Monocular UAV Motion Planning Method Based on Deep Reinforcement Learning
Man-Chen Hsueh, Chun Ku, Xiu-Zhi Chen, Yen‐Lin Chen · 2025
This paper presents a monocular UAV motion planning method based on the DRL method SDDPG. By processing image data with the self-proposed lightweight depth estimation model and a pretrained encoder, the information is sent into an improved Actor-Critic Network, which addresses overestimation issues and enhances learning efficiency. The experiments were conducted in Unreal Engine 4 and Airsim, which demonstrate the improvement of the motion planning ability, enabling UAVs to autonomously navigate and safely reach the defined destination.